Open Mind Tree

We want to build intelligent actors, not just intelligent thinkers. Indeed, it is not even clear how one could assess intelligence in a system that never acted – or, put otherwise, how a system could exhibit intelligence in the absence of action. -Martha Pollack, from Computers and Thought Lecture, IJCAI-91

DEFINITION OF THE AREA

GOOD PLACES TO START

GENERAL READINGS

• Also see:
  • Intelligent Agents. Chapter 2 of the textbook, Artificial Intelligence: A Modern Approach, by Stuart Russell and Peter Norvig. 1995
  • AI on the Web: Intelligent Agents, the resource companion to the textbook with links to reference material, people, research groups, books, companies and much more.
  • Some resources about wumpus world.

• Chapter One is also available online and that's where you'll find lots of useful information including an answer to the question "What Is Computational Intelligence?" and this summary of the common features of the aforementioned three agent tasks: "At one level of abstraction, they each have four tasks: Modeling the environment ... Evidential reasoning or perception ... Action ... Learning from past experience .... These tasks cut across all application domains."
• And be sure to check out their [http://www.aispace.org/|AIspace -Tools for Learning Computational Intelligence]]: "Here are some applets that are designed as tools for learning and exploring concepts in artificial intelligence. If you are teaching or learning about AI, you may use these applets freely." Two of the applets you'll find there are:
  • [http://aispace.org/robot/ |Robot Control]]: "A robot is an intelligent agent that perceives, reasons, and acts in time in an environment. It acts to achieve its assigned goals and at the same time avoids getting into undesired states. The robot applet provides a simulation of a robot perceiving and acting under the control of a set of customizable robot controller functions."
  • Planning: "Planning is essential for agents that act in an environment. To solve a goal intelligently, an agent needs to think about what it will do now and in the future. This applet demonstrates planning using the blockworld problem domain and STRIPS representation."

• Agent Architecture. Section 3.5 in The Role of Intelligent Systems in the National Information Infrastructure. The American Association for Artificial Intelligence. Daniel S. Weld, editor. (1995). "Agents, as we defined previously, are entities capable of autonomous goal-oriented behavior in some environment, often in the service of larger-scale goals external to themselves. The architecture of an agent is the computational structure that, along with the more dynamic knowledge represented within it, generates the agent’s behavior in the environment. The architecture must contain structures that enable representing knowledge (Subsection 3.1), representing and achieving goals (Subsection 3.3), interacting with the environment, and coping with unexpected occurrences. Moreover, for many domains, these capabilities must be exhibited in real time. Depending on the nature of the environment, other agents (either human or virtual) in the environment, and the kinds of task the agent should perform in the environment, other capabilities may also need to be supported in the agent’s architecture; for example, coordination and collaboration (Subsection 3.6), language use (Subsection 3.8), learning (Subsection 3.2), and humanlike behavior and affect."
• Intelligent Agent Architecture. Entry by Stanley J. Rosenschein in the MIT Encyclopedia of Cognitive Science. "Intelligent agent architecture is a model of an intelligent information-processing system defining its major subsystems, their functional roles, and the flow of information and control among them. ... An intelligent agent is a device that interacts with its environment in flexible, goal-directed ways, recognizing important states of the environment and acting to achieve desired results. Clearly, when designing a particular agent, many domain-specific features of the environment must be reflected in the detailed design of the agent. Still, the general form of the subsystems underlying intelligent interaction with the environment may carry over from domain to domain. Intelligent agent architectures attempt to capture these general forms and to enforce basic system properties such as soundness of reasoning, efficiency of response, or interruptibility. Many architectures have been proposed that emphasize one or another of these properties, and these architectures can be usefully grouped into three broad categories: the deliberative, the reactive, or the distributed."
• Autonomous Agents as Embodied AI. By Stan Franklin. (1997). Cybernetics and Systems, 28(6): 499-520. "This paper is primarily concerned with answering two questions: What are necessary elements of embodied architectures? How are we to proceed in a science of embodied systems?"
• What sort of architecture is required for a human-like agent? By Aaron Sloman, School of Computer Science & Cognitive Science Research Centre at The University of Birmingham. "A complete functioning agent, whether biological, or simulated in software, or implemented in the form of a robot, needs an integrated collection of diverse but interrelated capabilities, i.e. an architecture."
  • Also see the slides from: Varieties of Evolvable Minds OR How to think about architectures for human-like and other agents OR How to Turn Philosophers of Mind into Engineers - presented in Oxford on January 22, 2001.
  • Also available: the expanded version of the paper.
• Pandemonium, Demons & Oliver Selfridge (see: Namesakes)

• Preface. By Daniel Shapiro, Pauline Berry, John Gersh, and Nathan Schurr. "This document discusses what it will take to enable a future in which intelligent agents play a significant role in personal and professional lives."